Viewing enriched Twitter post
This is Huge! 🥳 Half of the conversations around LLMs are “Will this fit on my GPU[s]?” And this calculator makes it much easier. There are some important nuances for LoRA and I took notes on that here: https://t.co/Bct28Wwhea https://t.co/MilXje5IVB
{
"media": [
{
"url": "https://pbs.twimg.com/media/F4oMkGracAEhtyb.png",
"type": "photo"
},
{
"url": "https://pbs.twimg.com/media/F4oMn_Ua0AAEaLG.png",
"type": "photo"
}
],
"nlp": {
"sentiment": "positive",
"processed_at": "2025-08-06T12:54:52.830325"
},
"score": 1.0,
"scored_at": "2025-08-09T13:46:07.546870",
"import_source": "manual_curation_2023",
"score_components": {
"author": 0.09,
"engagement": 0.1364582394846385,
"quality": 0.13999999999999999,
"source": 0.15,
"nlp": 0.1,
"recency": 0.010000000000000002
},
"source_tagged_at": "2025-08-09T13:43:12.091337",
"enriched": true,
"enriched_at": "2025-08-09T13:43:12.091341",
"links_checked": true,
"checked_at": "2025-08-10T10:32:37.574055",
"original_structure": "had_media_only",
"enhanced_from_raw_response": true,
"enhanced_at": "2025-08-13T17:10:00Z",
"extracted_from_extended_entities": true,
"extracted_at": "2025-08-14T04:30:00Z"
}{
"user": {
"created_at": "2012-09-15T18:45:02.000Z",
"default_profile_image": false,
"description": "Researcher focusing on LLMs: https://t.co/iVZDFdIQiE \n\nPreviously, dev tools and infra for ML. Ex @Github, @Airbnb, @DataRobot. @fastdotai core contributor.",
"fast_followers_count": 0,
"favourites_count": 9874,
"followers_count": 17039,
"friends_count": 1515,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 422,
"location": "Portland, OR",
"media_count": 626,
"name": "Hamel Husain",
"normal_followers_count": 17039,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/825766640/1661535109",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1287206199088173057/ixE4fKy1_normal.jpg",
"screen_name": "HamelHusain",
"statuses_count": 7995,
"translator_type": "none",
"url": "https://t.co/mBx5zIJYEA",
"verified": false,
"withheld_in_countries": [],
"id_str": "825766640"
},
"id": "1696182174024962549",
"conversation_id": "1696182174024962549",
"full_text": "This is Huge! 🥳 Half of the conversations around LLMs are “Will this fit on my GPU[s]?” And this calculator makes it much easier. \n\nThere are some important nuances for LoRA and I took notes on that here:\n\nhttps://t.co/Bct28Wwhea https://t.co/MilXje5IVB",
"reply_count": 8,
"retweet_count": 69,
"favorite_count": 397,
"hashtags": [],
"symbols": [],
"user_mentions": [],
"urls": [
{
"url": "https://t.co/Bct28Wwhea",
"expanded_url": "https://hamel.dev/notes/llm/03_estimating_vram.html",
"display_url": "hamel.dev/notes/llm/03_e…"
}
],
"media": [
{
"media_url": "https://pbs.twimg.com/media/F4oMkGracAEhtyb.png",
"type": "photo"
},
{
"media_url": "https://pbs.twimg.com/media/F4oMn_Ua0AAEaLG.png",
"type": "photo"
}
],
"url": "https://twitter.com/HamelHusain/status/1696182174024962549",
"created_at": "2023-08-28T15:25:18.000Z",
"#sort_index": "1696182174024962549",
"view_count": 106239,
"quote_count": 3,
"is_quote_tweet": true,
"is_retweet": false,
"is_pinned": false,
"is_truncated": false,
"quoted_tweet": {
"user": {
"created_at": "2016-04-15T16:54:07.000Z",
"default_profile_image": false,
"description": "🤗 MLSE working on Accelerate | Passionate about Open Source | Nerd who enjoys touching the grass | #ADHD | He/Him/We",
"fast_followers_count": 0,
"favourites_count": 28273,
"followers_count": 8704,
"friends_count": 327,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 193,
"location": "",
"media_count": 1545,
"name": "Zach Mueller",
"normal_followers_count": 8704,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/721018777664626688/1665150558",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1571624677080010764/FWhg6yLl_normal.jpg",
"screen_name": "TheZachMueller",
"statuses_count": 13075,
"translator_type": "none",
"url": "https://t.co/yBmBqMwesX",
"verified": false,
"withheld_in_countries": [],
"id_str": "721018777664626688"
},
"id": "1696157965890339148",
"conversation_id": "1696157965890339148",
"full_text": "Excited to announce a new @huggingface space to help with one of machine learning's biggest questions:\n\nHow much space does {X} model take in vRAM? And most importantly: when using `device_map=\"auto\"`\n\nhttps://t.co/kmQCuPeAdM https://t.co/b2xQRreucD",
"reply_count": 15,
"retweet_count": 123,
"favorite_count": 522,
"hashtags": [],
"symbols": [],
"user_mentions": [
{
"id_str": "778764142412984320",
"name": "Hugging Face",
"screen_name": "huggingface",
"profile": "https://twitter.com/huggingface"
}
],
"urls": [
{
"url": "https://t.co/kmQCuPeAdM",
"expanded_url": "https://huggingface.co/spaces/hf-accelerate/model-memory-usage",
"display_url": "huggingface.co/spaces/hf-acce…"
}
],
"media": [
{
"media_url": "https://pbs.twimg.com/ext_tw_video_thumb/1696151830001029120/pu/img/jvMdpLrR8kxAYeLT.jpg",
"type": "video",
"video_url": "https://video.twimg.com/ext_tw_video/1696151830001029120/pu/vid/1920x1080/QKPyE4aTLhH_0RwI.mp4?tag=14"
}
],
"url": "https://twitter.com/TheZachMueller/status/1696157965890339148",
"created_at": "2023-08-28T13:49:06.000Z",
"#sort_index": "1696182174024962600",
"view_count": 132835,
"quote_count": 15,
"is_quote_tweet": false,
"is_retweet": false,
"is_pinned": false,
"is_truncated": false
},
"startUrl": "https://twitter.com/hamelhusain/status/1696182174024962549"
}